A command that creates a monthly closing report for a client company. Monthly closing is the accounting process of summarizing and reviewing a month's transactions.

It helps produce transaction, category, month-over-month anomaly, and classification-quality summaries for a named company and month.

It gathers financial totals, category changes, classification methods, and possible anomalies into one report for review.

report — Command for Claude Code by michielinksee

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/michielinksee/bantou

Made for: Claude Code.

Or install bantou, the plugin that ships this one along with the rest of its 5 skills, 6 commands, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/michielinksee/bantou/report.svg)](https://agentmods.dev/commands/michielinksee/bantou/report)

Your own site

<a href="https://agentmods.dev/commands/michielinksee/bantou/report"><img src="https://agentmods.dev/badge/commands/michielinksee/bantou/report.svg" alt="Measured on agentmods" height="20"></a>

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 343 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00012	$0.00343
Opus 5	$0.00006	$0.00171
Sonnet 5	$0.00002	$0.00069
Haiku 4.5	$0.00001	$0.00034

Measured 8d ago against content hash 1fc2f9dfd48b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

report scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/claude-for-jp-accounting/commands/report.md · 58 lines

What it actually says

/bantou:report

Generate a monthly closing report for a client company.

Usage

/jp-accounting:report <company-name> <month>

Examples

/jp-accounting:report 株式会社サンプル 2026-01
/jp-accounting:report "ABC Trading" 2026-03
/jp-accounting:report サンプル商事 202604

Input

company-name — The client company name (partial match supported)
month — Target month in YYYY-MM or YYYYMM format

Generated sections

Transaction summary

Total count, total expenditure, total revenue
Classification method breakdown (memory / keyword / AI / manual)

Category breakdown (勘定科目別集計)

Each category with count, amount, and percentage
Sorted by amount descending

Anomaly detection (前月比異常検知)

Categories with month-over-month change exceeding +/- 50%
Each anomaly includes current amount, previous amount, and change %
Flagged for tax accountant review

Classification quality

Stage 0 exclusion count
Memory hit rate
AI fallback rate
Manual review count

Output format

Generated as structured Markdown displayed directly in the terminal. Can be saved to a file, converted to PDF, or included in email.

Notes

Uses data from the most recent classification run
Month-over-month comparison requires at least 2 months of data
The first month will not include anomaly detection

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 58 lines · 12 tokens per session scan A 1fc2f9dfd48b

Subscribe to this mod's changes

report is a command published in the GitHub repository michielinksee/bantou (2 stars, last pushed 17d ago), licensed MIT. It adds 12 tokens to every session and 343 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Documents Finance and fintech accounting ai-agent automation bookkeeping claude fintech

report